• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.79-89
• /
• 2016

In this paper, we proposed the object classification method using genetic and dynamic random forest consisting of optimal combination of unit tree. The random forest can ensure good generalization performance in combination of large amount of trees by assigning the randomization to the training samples and feature selection, etc. allocated to the decision tree as an ensemble classification model which combines with the unit decision tree based on the bagging. However, the random forest is composed of unit trees randomly, so it can show the excellent classification performance only when the sufficient amounts of trees are combined. There is no quantitative measurement method for the number of trees, and there is no choice but to repeat random tree structure continuously. The proposed algorithm is composed of random forest with a combination of optimal tree while maintaining the generalization performance of random forest. To achieve this, the problem of improving the classification performance was assigned to the optimization problem which found the optimal tree combination. For this end, the genetic algorithm methodology was applied. As a result of experiment, we had found out that the proposed algorithm could improve about 3~5% of classification performance in specific cases like common database and self infrared database compare with the existing random forest. In addition, we had shown that the optimal tree combination was decided at 55~60% level from the maximum trees.

• Journal of Korean Society of Forest Science
• /
• v.90 no.1
• /
• pp.155-160
• /
• 2001

Changes in genetic diversity after seed-tree practice were simulated in test plantation of tulip tree at Sokdal-ri, Banwol-myon, Hwasung-gun, Kyungki Provence. I-SSR markers were analyzed in a total of 305 tulip trees. A total of 89 amplicon variants were observed by PCR with 9 I-SSR primers. Genetic diversity for 305 trees was relatively high (S. I. =0.4532). Individuals originated from the seed orchards in U.S.A. showed the highest level of genetic diversity (0.4530), those from Anyang showed the medium level (0.4152), and those from Cheonbuk showed the lowest (0.3929). Simulation of seed-tree practice accompanied by 2 consecutive thinnings was performed on the basis of morphological characteristics and planted distances of the individual trees, which left 37 trees as candidates for seed-trees. Decreasing rate of genetic diversity within seed sources was greatest for individuals from Cheonbuk (28.3%), moderate for those from Anyang (16.3%), and smallest for those from U.S.A. (8.0%). In spite of little difference in decreasing rate of individuals for the 3 seed sources (87.5~88.2%), large difference in decreasing rate of genetic diversity within seed sources might be due to difference in number of mother trees for the 3 seed sources. For example, whereas individuals originated from the seed orchard in U.S.A., which showed the smallest decreasing rate of genetic diversity, might be originated from relatively large number of mother trees, those from Anyang and Cheonbuk might be originated from relatively small number of mother trees. Although mean of 17.5% of the genetic diversity within seed sources was decreased through 2 consecutive thinnings, a decrease in genetic diversity for the whole individuals (37 trees) was only 6.1%. This observation suggests that the seed-tree practice on the basis of the criteria established in the present study may not result in great reduction in overall genetic diversity of the progenies.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.25 no.4
• /
• pp.151-162
• /
• 2022

Recently, the forests in Korea have accumulated damage due to continuous forest disasters, and the need for technologies to monitor forest managements is being issued. The size of the affected area is large terrain, technologies using drones, artificial intelligence, and big data are being studied. In this study, a standard dataset were conducted to develop an algorithm that automatically detects suspicious trees damaged by forest pests using deep learning and drones. Experiments using the YOLO model among object detection algorithm models, the YOLOv4-P7 model showed the highest recall rate of 69.69% and precision of 69.15%. It was confirmed that YOLOv4-P7 should be used as an automatic detection algorithm model for trees suspected of being damaged by forest pests, considering the detection target is an ortho-image with a large image size.

• Journal of People, Plants, and Environment
• /
• v.24 no.6
• /
• pp.619-628
• /
• 2021

Background and objective: Native to the limestone zones of the Korean Peninsula, Zabelia tyaihyonii is a popular plant for landscaping. As it is now classified as a rare species, the conservation of its genetic resources is necessary. Methods: In this study, which aimed to understand the morphological variation of Z. tyaihyonii, 18 characteristics of Z. tyaihyonii from five habitats were examined. Results: Of these 18 characteristics, 16 characteristics showed significant differences among sites, and the coefficient of variation ranged from 5.4% (for corolla lobe number) to 31.3% (for flower number). Notable variations were observed in the size of flower and calyx lobe. When the corolla length and calyx lobe length were used as the classification key of Z. tyaihyonii, the sites were divided into those with small, intermediate, and large values. Hair was observed on the filament of all samples, a finding which conflicts with an earlier report. Rather than classifying Z. tyaihyonii into different species on the basis of corolla length (COL) and calyx lobe length (CALL) values, we recommend modifying the species description to incorporate the variation in these characteristics of interest. Principal component analysis results showed that the first main component was highly correlated with the traits related to the size of the calyx lobe (length: 0.819, width: 0.758), and the second main component was highly correlated with the traits related with the size of the inflorescence (length: 0.790, width: 0.626). Conclusion: Several notable variations were identified among the characteristics related to inflorescence and calyx lobe. There is little genetic exchange among groups, or each group is influenced by micro environmental factors, because sites that are located nearby. In addition, the difference between COL and CALL, which is used as the classification key for Z. tyaihyonii, was divided into small group, large group, and intermediate group, regardless of the sites' geographical distance.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.6
• /
• pp.113-120
• /
• 2024

With the advancement of information and communication technology, we can easily generate various forms of data in our daily lives. To efficiently manage such a large amount of data, systematic classification into categories is essential. For effective search and navigation, data is organized into a tree-like hierarchical structure known as a category tree, which is commonly seen in news websites and Wikipedia. As a result, various techniques have been proposed to classify large volumes of documents into the terminal nodes of category trees. However, document classification methods using category trees face a problem: as the height of the tree increases, the number of terminal nodes multiplies exponentially, which increases the probability of misclassification and ultimately leads to a reduction in classification accuracy. Therefore, in this paper, we propose a new node expansion-based classification algorithm that satisfies the classification accuracy required by the application, while enabling detailed categorization. The proposed method uses a greedy approach to prioritize the expansion of nodes with high classification accuracy, thereby maximizing the overall classification accuracy of the category tree. Experimental results on real data show that the proposed technique provides improved performance over naive methods.

• Journal of Korean Society for Atmospheric Environment
• /
• v.17 no.E2
• /
• pp.61-70
• /
• 2001

In recent years there have been growing interests in the potential environmental effects of global climate change. Of specific interests is the role that climate change may play in altering natural volatile organic compound.(NVOC) emissions from trees and the subsequent impact of this perturbation on air quality and ozone formation. A novel vegetation enclosure chamber method was designed and constructed of Tedlar in order to estimate more accurate and precise NVOC emission rates of either small whole plants or the branches of large trees. The enclosure chamber was initially tested in the laboratory and also successfully evaluated in the field. Overall precision for this enclosure was estimated as RSD<10%(n=9). The overall errors associated with the enclosure method in a laboratory system might be relatively small (say<$\pm$15%); however, they might be rather large(say$\pm$40%) in a field-based system. Two consecutive samples were collected on each sampling day from the two pine species during the test period. Slash pine studies showed that the absolute percentage difference between the first and second samples varied from 0.33 to 29%. The percent differences between consecutive emission for loblolly pines varied from 0.74 to 24.2%.

• Proceedings of the National Institute of Ecology of the Republic of Korea
• /
• v.2 no.2
• /
• pp.76-81
• /
• 2021

With continuous decline of Philippine forest cover, sustainable forest management and restoration are essential to restore destroyed forest ecosystems. Unfortunately, of ten most planted trees in reforestation projects in the Philippines, eight are exotic species, with large leaf mahogany (Swietenia macrophylla) being the most dominant. In this study, effect of Swietenia macrophylla in reforestation projects on native tree species was evaluated. Effects of S. macrophylla leaf litter, frequency, and canopy closure on the growth of the Philippine native species Pterocarpus indicus were investigated. Results showed that S. macrophylla leaf litter significantly inhibited the growth of P. indicus seedlings based on root collar-to-shoot height. The standardized growth rate of seedlings in plots without S. macrophylla leaf litter was significantly higher than the growth rate of seedlings in plots with leaf litter. Furthermore, there was no significant difference in the standardized growth rate of seedlings between plots without leaf litter and a control plot. On the contrary, S. macrophylla tree frequency and canopy closure showed no significant effect. These results attest to the negative effect of widely planted S. macrophylla to a valuable Philippine native tree P. indicus. With accumulating scientific evidence about negative effects of S. macrophylla on native trees, discontinued use in tree planting and reforestation efforts with active management of restoration sites previously planted with large leaf mahogany are needed.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.1
• /
• pp.37-46
• /
• 2010

A Suffix Tree is an efficient data structure that exposes the internal structure of a string and allows efficient solutions to a wide range of complex string problems, in particular, in the area of computational biology. However, as the biological information explodes, it is impossible to construct the suffix trees in main memory. We should find an efficient technique to construct the trees in a secondary storage. In this paper, we present a method for constructing a suffix tree in a disk for large set of DNA strings using new index scheme. We also show a typical application example with a suffix tree in the disk.

• Wind and Structures
• /
• v.5 no.2_3_4
• /
• pp.291-300
• /
• 2002

An efficient large eddy simulation algorithm is used to compute surface pressure distributions on an eleven story (target) building on the NIST campus. Local meteorology, neighboring buildings, topography and large vegetation (trees) all play an important part in determining the flows and therefore the pressures experienced by the target. The wind profile imposed at the upstream surface of the computational domain follows a power law with an exponent representing a suburban terrain. This profile accounts for the flow retardation due to friction from the surface of the earth, but does not include fluctuations that would naturally occur in this flow. The effect of neighboring buildings on the time dependent surface pressures experienced by the target is examined. Comparison of the pressure fluctuations on the single target building alone with those on the target building in situ show that, owing to vortices shed by the upstream buildings, fluctuations are larger when such buildings are present. Even when buildings are lateral to or behind the target, the pressure disturbances generate significantly different flows around this building. A simple grid-free mathematical model of a tree is presented in which the trunk and the branches are each represented by a collection of spherical particles strung together like beads on a string. The drag from the tree, determined as the sum of the drags of the component particles, produces an oscillatory, spreading wake of slower fluid, suggesting that the behavior of trees as wind breakers can be modeled usefully.

• Journal of Ecology and Environment
• /
• v.41 no.3
• /
• pp.85-92
• /
• 2017

Unmanned aerial vehicles (UAVs) are a new and yet constantly developing part of forest inventory studies and vegetation-monitoring fields. Covering large areas, their extensive usage has saved time and money for researchers and conservationists to survey vegetation for various data analyses. Post-processing imaging software has improved the effectiveness of UAVs further by providing 3D models for accurate visualization of the data. We focus on determining the coniferous tree coverage to show the current advantages and disadvantages of the orthorectified 2D and 3D models obtained from the image photogrammetry software, Pix4Dmapper Pro-Non-Commercial. We also examine the methodology used for mapping the study site, additionally investigating the spread of coniferous trees. The collected images were transformed into 2D black and white binary pixel images to calculate the coverage area of coniferous trees in the study site using MATLAB. The research was able to conclude that the 3D model was effective in perceiving the tree composition in the designated site, while the orthorectified 2D map is appropriate for the clear differentiation of coniferous and deciduous trees. In its conclusion, the paper will also be able to show how UAVs could be improved for future usability.